Neuro-fuzzy feature selection approach based on linguistic hedges for medical diagnosis

The use of soft computing techniques in disease diagnosis is increasing. This is mainly because the effectiveness of classification and prediction systems has been improved to help physicians in diagnosing. One of the core issues in medical data analysis and mining is the curse of dimensionality; particularly, the medical datasets are characterised by relatively few instances and presented in a high-dimensional feature space. Feature selection plays an important role in building classification systems. It can not only reduce the dimension of data, but also lower the computation costs and gain a good classification performance. In this paper, a feature selection method based on linguistic hedges neural-fuzzy classifier (LHNFC) is presented for medical diagnosis. This classifier is used to achieve very fast, simple and efficient diagnosis. The results indicated that use of linguistic hedges in adaptive neural-fuzzy classifier improves the success of the classifier. Applying LHNFCSF not only reduces the dimensions of the problem, but also improves classification performance by discarding redundant, noise-corrupted, or unimportant features. The results strongly suggest that the proposed method not only helps to reduce the dimensionality of large datasets but also can speed up the computation time of a learning algorithm and simplify the classification tasks.